Exact Test Research Articles

Cross-sectional study to evaluate the utility of elastic tissue staining in primary cicatricial alopecia

Background and aimsDiagnosing end-stage primary cicatricial alopecia (PCA) on routine histology is challenging since the major diagnostic feature (inflammatory infiltrate) may be minimal or absent. This study aimed to assess...

Relationship detection for manipulation in object stacking scene with fully connected CRF

Relationship detection for manipulation in object stacking scenes is an actively studied problem in recent years. Since the stacked objects may occlude and block each other, it is necessary to model relationships among them for safety. Almost all existing solutions to this problem model object relationships separately and ignore their dependencies on each other. In this paper, we propose a fully connected Conditional Random Field (CRF) to impose global constraints on the object stacking scenes. Since the inference of fully connected CRF is usually intractable, we propose efficient methods for the exact inference and the variational inference to solve the proposed CRFs. Furthermore, the variational inference is implemented as an RNN for end-to-end training. Experimental results on Visual Manipulation Relationship Dataset VMRD and REGRAD suggest that the proposed CRF can, with a clear margin, improve the accuracy of manipulation relationship detection in object stacking scenes. Finally, the proposed models are also deployed on a physical robot to build a relation-aware grasping system. Results demonstrate that our algorithms can be generalized to real-world scenes well and help the robot perform safe grasping in object stacking scenes.

Antegrade Continence Enema Alone for the Management of Functional Constipation and Segmental Colonic Dysmotility (ACE-FC): A Pediatric Colorectal and Pelvic Learning Consortium Study.

The purpose of the study was to determine if antegrade continence enema (ACE) alone is an effective treatment for patients with severe functional constipation and segmental colonic dysmotility. A retrospective study of patients with functional constipation and segmental colonic dysmotility who underwent ACE as their initial means of management. Data was collected from six participating sites in the Pediatric Colorectal and Pelvic Learning Consortium. Patients who had a colonic resection at the same time as an ACE or previously were excluded from analysis. Only patients who were 21 years old or younger and had at least 1-year follow-up after ACE were included. All patients had segmental colonic dysmotility documented by colonic manometry. Patient characteristics including preoperative colonic and anorectal manometry were summarized, and associations with colonic resection following ACE were evaluated using Fisher's exact test and Wilcoxon rank-sum test. p-Values of less than 0.05 were considered significant. Statistical analyses and summaries were performed using SAS version 9.4 (SAS Institute Inc., Cary, North Carolina, United States). A total of 104 patients from 6 institutions were included in the study with an even gender distribution (males n = 50, 48.1%) and a median age of 9.6 years (interquartile range 7.4, 12.8). At 1-year follow-up, 96 patients (92%) were successfully managed with ACE alone and 8 patients (7%) underwent subsequent colonic resection for persistent symptoms. Behavioral disorder, type of bowel management, and the need for botulinum toxin administered to the anal sphincters was not associated with the need for subsequent colonic resection. On anorectal manometry, lack of pelvic floor dyssynergia was significantly associated with the need for subsequent colonic resection; 3/8, 37.5% without pelvic dyssynergia versus 1/8, 12.5% (p = 0.023) with pelvic dyssynergia underwent subsequent colonic resection. In patients with severe functional constipation and documented segmental colonic dysmotility, ACE alone is an effective treatment modality at 1-year follow-up. Patients without pelvic floor dyssynergia on anorectal manometry are more likely to receive colonic resection after ACE. The vast majority of such patients can avoid a colonic resection.

Exact burst-size distributions for gene-expression models with complex promoter structure

In prokaryotic and eukaryotic cells, most genes are transcribed in a bursty fashion on one hand and complex gene regulations may lead to complex promoter structure on the other hand. This raises an unsolved issue: how does promoter structure shape transcriptional bursting kinetics characterized by burst size and frequency? Here we analyze stochastic models of gene transcription, which consider complex regulatory mechanisms. Notably, we develop an efficient method to derive exact burst-size distributions. The analytical results show that if the promoter of a gene contains only one active state, the burst size indeed follows a geometric distribution, in agreement with the previous result derived under certain limiting conditions. However, if it contains a multitude of active states, the burst size in general obeys a non-geometric distribution, which is a linearly weighted sum of geometric distributions. This superposition principle reveals the essential feature of bursting kinetics in complex cases of transcriptional regulation although it seems that there has been no direct experimental confirmation. The derived burst-size distributions not only highlight the importance of promoter structure in regulating bursting kinetics, but can be also used in the exact inference of this kinetics based on experimental data.

FIB-4 Reliability in Patients With Severe Obesity: Lower Cutoffs Needed?

Liver biopsy is the gold standard to evaluate hepatic fibrosis; however, it has many drawbacks, especially in patients with severe obesity. Noninvasive testing such as the FIB-4 score is increasingly being used as the initial screening tool to identify patients at risk for advanced fibrosis. The broader applicability of FIB-4 and the precision of its cutoff values remain uncertain in metabolic dysfunction-associated steatotic liver disease and patients with severe obesity. Our study explored the correlation between FIB-4 scores and intraoperative liver biopsy in patients with severe obesity undergoing bariatric surgery. A total of 632 patients with severe obesity underwent preoperative vibration-controlled transient elastography and intraoperative liver biopsy during bariatric surgery from January 2020 to August 2021. Variables collected included patient demographics, laboratory values, abdominal ultrasound, vibration-controlled transient elastography, and liver biopsy results. ANOVA 1-way test, χ 2 tests, and Fisher exact tests were used for quantitative and qualitative variables, respectively. The 95% CIs for the mean FIB-4 scores were used to generate surrogate cutoff values. The proposed FIB-4 cutoffs for F0-1, F2, F3, and F4 were 0.62 (CI: 0.59, 0.64), 0.88 (0.74, 1.01), 1.24 (0.94, 1.54), and 1.53 (0.82, 2.24), respectively. Area under the curve (AUC) methods were used to compare traditional to proposed cutoff values. Applying the traditional FIB-4 cutoffs to approximate advanced fibrosis yielded an AUC of 0.5748. Use of the proposed FIB-4 cutoffs increased the AUC to 0.6899. The proposed FIB-4 cutoffs correctly identified 40 patients with biopsy-proven advanced fibrosis (F3-F4), all of which would have been missed using traditional cutoffs. Our study revealed that the use of the currently accepted FIB-4 cutoffs as the screening modality for identifying patients with advanced fibrosis due to metabolic dysfunction-associated steatotic liver disease is insufficient and will result in missing patients with histologically confirmed advanced fibrosis. Use of the revised FIB-4 scores should be considered to diagnose patients with severe obesity at high risk of liver disease progression.

Neural Operator Variational Inference Based on Regularized Stein Discrepancy for Deep Gaussian Processes.

Deep Gaussian process (DGP) models offer a powerful nonparametric approach for Bayesian inference, but exact inference is typically intractable, motivating the use of various approximations. However, existing approaches, such as mean-field Gaussian assumptions, limit the expressiveness and efficacy of DGP models, while stochastic approximation can be computationally expensive. To tackle these challenges, we introduce neural operator variational inference (NOVI) for DGPs. NOVI uses a neural generator to obtain a sampler and minimizes the regularized Stein discrepancy (RSD) between the generated distribution and true posterior in L2 space. We solve the minimax problem using Monte Carlo estimation and subsampling stochastic optimization techniques and demonstrate that the bias introduced by our method can be controlled by multiplying the Fisher divergence with a constant, which leads to robust error control and ensures the stability and precision of the algorithm. Our experiments on datasets ranging from hundreds to millions demonstrate the effectiveness and the faster convergence rate of the proposed method. We achieve a classification accuracy of 93.56 on the CIFAR10 dataset, outperforming state-of-the-art (SOTA) Gaussian process (GP) methods. We are optimistic that NOVI possesses the potential to enhance the performance of deep Bayesian nonparametric models and could have significant implications for various practical applications.

Faster-BNI: Fast Parallel Exact Inference on Bayesian Networks

Faster-BNI: Fast Parallel Exact Inference on Bayesian Networks

Exact Inference for Common Odds Ratio in Meta-Analysis with Zero-Total-Event Studies

AbstractStemming from the high-profile publication of Nissen and Wolski (N Engl J Med 356:2457–2471, 2007) and subsequent discussions with divergent views on how to handle observed zero-total-event studies, defined to be studies that observe zero number of event in both treatment and control arms, the research topic concerning the common odds ratio model with zero-total-event studies remains to be an unresolved problem in meta-analysis. In this article, we address this problem by proposing a novel repro samples method to handle zero-total-event studies and make inference for the common odds ratio. The development explicitly accounts for the sampling scheme that generates the observed data and does not rely on any large sample approximations. It is theoretically justified with a guaranteed finite-sample performance. Simulation studies are designed to demonstrate the empirical performance of the proposed method. It shows that the proposed confidence set, although a little conservative, achieves the desired empirical coverage rate in all situations. The development also shows that the zero-total-event studies contain meaningful information and impact the inference for the common odds ratio. The proposed method is used to perform a meta-analysis of the 48 trials reported in Nissen and Wolski (N Engl J Med 356:2457–2471, 2007) as well

Bayesian model-based damage detection in engineering systems using Invertible Neural Networks

This study explores the application of BayesFlow, a state-of-the-art deep learning technique for approximate Bayesian inference, in the context of Structural Health Monitoring (SHM), and specifically, model-based damage detection. BayesFlow diverges from other likelihood-free methods by not relying on predefined summary statistics, but learning optimal ones from the simulations via invertible neural networks. It is also capable of performing almost instantaneous inference for an arbitrary number of datasets, which is ideal for real-time applications such as bridge monitoring systems. The effectiveness of the proposed approach is demonstrated with a small scale bridge use case with synthetic measurements for different testing scenarios. Across all sub-cases, BayesFlow is able to determine both the damage location and severity with a high accuracy, while the credible intervals are close to those obtained under an exact Bayesian inference approach with the true likelihood.

The Effect of Lavender Aromatherapy on Heart Rate, Blood Pressure, and Perceived Stress Among Cardiac Rehabilitation Patients: A Pilot Study.

The purpose of this study was to test the efficacy of lavender aromatherapy via inhalation as a stress management modality for patients in cardiac rehabilitation. This was a quasi-experimental design. Aromatherapy was provided via inhalation to participants before a cardiac rehabilitation session over 8 minutes using lavender essential oil. The same protocol was used in the non-aromatherapy session without the essential oil. Blood pressure and radial pulse were measured, and subjective data were also collected including assessment of stress level (1-10 scale) and affect using the Positive and Negative Affect Schedule (PANAS). Analyses were performed using SPSS Statistics version 20. Quantitative measures were analyzed using Mann-Whitney nonparametric equivalent to the t test. Inferential measures were analyzed using the χ 2 or Fisher's exact test. In the outpatient cardiac rehabilitation program, 25 patients participated in this study. The average change in negative affect (PANAS-) between pre and post-aromatherapy compared with pre- and post-non-aromatherapy sessions was statistically significant. Results showed a reduction in blood pressure following both aromatherapy and non-aromatherapy sessions with no statistical significance between sessions. Heart rate decreased equally post-aromatherapy and non-aromatherapy sessions. Aromatherapy may be a useful stress management tool for cardiac rehabilitation patients.

Sustained inflation and chest compression versus 3:1 chest compression to ventilation ratio during cardiopulmonary resuscitation of asphyxiated newborns (SURV1VE): A cluster randomised controlled trial

ObjectiveIn newborn infants requiring chest compression (CC) in the delivery room (DR) does continuous CC superimposed by a sustained inflation (CC+SI) compared with a 3:1 compression:ventilation (3:1 C:V) ratio decreases...

The effect of outcome-based education on clinical performance and perception of pediatric care of the third-year nursing students in Mongolia.

Mongolian government has set improvement of clinical proficiency of nursing students as one of its priorities. Nursing professionals have the sentinel role in providing healthcare services in rural areas. Outcome-based education (OBE) offers a promising pedagogical approach to actively mentally engage students to strengthen their clinical proficiencies. We implemented a pilot project with the objective of comparing students' clinical performance under OBE with our traditional didactic techniques. The researchers implemented a non-equivalent two-armed quasi-experimental post-test-only' design approach study. The intervention arm (n = 34) received OBE pediatric training, while the control arm (n = 32) received the traditional pedagogical pediatric nursing training. Each arm of the study completed 16 hours of theory, 32 hours of clinical skills practice and 32 hours of seminars in pediatric nursing care. Data were collected using a five-section instrument, Demographic, Competency Inventory, Nursing Students' Satisfaction, Course Experience, and Objective Structured Clinical Examination. Performance and knowledge proficiencies were evaluated by applying the two-sided independent T-test. The distributions of categorical variables were assessed by Fisher's exact test or chi-squared test of significance. The intervention arm had higher mean score value in the competency inventory ([Formula: see text] = 238.70, SD = ± 23.07) compared to the control arm ([Formula: see text] = 222.11, SD = ± 39.94) (P = 0.04); similarly, the mean value for nursing students' satisfaction was higher for the intervention arm ([Formula: see text] = 117.87, SD = ± 15.94) compared to the control group ([Formula: see text] = 109.76, SD = ± 16.94) (P = 0.049). Additionally, the difference in the mean value for course experience questionnaire between the intervention arm ([Formula: see text] = 125.33, SD = ± 19.30) and the control arm ([Formula: see text] = 110.41, SD = ± 11.28) was statistically significant (P = 0.0001). Finally, the intervention arm had a higher mean value ([Formula: see text] = 85.40, SD = ± 6.11) for objective structural clinical examination compared to the control arm ([Formula: see text] = 81.56, SD = ± 7.01) (P = 0.023). OBE pedagogical approach offers promising benefits to improving nursing students' clinical competencies; additionally, the OBE approach seems to increase students' satisfactions with their clinical curriculum.

Change in eating habits after 2 years of pandemic restrictions among adolescents living in a city in northern Italy: results of the COALESCENT Observational Study (Change amOng ItAlian adoLESCENTs)

BackgroundLockdown measures during the recent pandemic, due to the novel COVID-19, affected several other aspects of lifestyle, but little is known about their long-term impact, especially among adolescents. Our study...

Resource setting impacts neonatal but not maternal survival in bitches treated for dystocia: 243 cases (2015-2020).

To compare maternal and fetal outcomes of dystocia managed surgically and nonsurgically at referral hospitals (RHs) versus community medicine clinics (CMCs), determine the rate of C-section, and evaluate the incidence of hypoglycemia and hypocalcemia in bitches presented with dystocia. Bitches presented with dystocia at 2 RHs and 2 CMCs. Information on signalment, presence of hypoglycemia and/or hypocalcemia, diagnostic imaging performed, nonsurgical and surgical interventions performed, maternal and fetal outcomes, and total cost of care was obtained from the electronic medical records of bitches presenting for dystocia between October 2015 and October 2020. Descriptive statistics were performed and outcome compared between RHs and CMCs using a Fisher exact test, with a P < .05 considered significant. 230 bitches were evaluated with 243 separate episodes of dystocia, with 183 (75%) episodes treated at an RH and 60 (25%) at a CMC. There was a low incidence of hypoglycemia (5% [9/178]) and ionized hypocalcemia (1% [2/164]). Seventy-three percent (177/243) of bitches underwent surgical intervention, 25% (61/243) received nonsurgical management, and 2% (5/243) transferred to their primary veterinarian. There was no difference in survival for bitches operated at an RH compared with a CMC. However, bitches operated at an RH were more likely (P = .04) to be discharged with at least 1 live neonate. In bitches diagnosed with dystocia, hypoglycemia and hypocalcemia were rare. The majority of bitches underwent a C-section. The setting where the C-section was performed did not impact maternal survival.

Off-Label Reduced Dose Apixaban in Older Adults With Atrial Fibrillation and Associated Outcomes.

Apixaban is commonly used to prevent stroke in older adults with nonvalvular atrial fibrillation (AF). Although its package insert has specific dose reduction criteria, providers may dose reduce outside of these parameters based on clinical scenarios. The primary objective was to determine the incidence of apixaban off-label reduced dosing, while secondarily determining the safety and efficacy outcomes associated with such dosing. A retrospective analysis of patients aged 65 and older with orders for apixaban for AF was institutional review board (IRB)-approved and conducted across 3 academic medical centers. Patients receiving off-label reduced-dose apixaban (ie, "underdosed") were matched to a cohort of patients dosed according to the package insert at the standard dosing (5 mg twice daily) using stratified random sampling. Secondary outcomes included 1-year incidence of major bleeding, clinically relevant non-major bleeding (CRNMB), stroke or transient ischemic attack (TIA), and mortality. The Fisher exact tests were used to compare between-group differences. Of the 1172 patients meeting initial inclusion criteria, 201 (17%) were dosed off-label, with 175 (15%) "underdosed." The 147 "underdosed" patients with documented follow-up were matched with 139 patients receiving standard Food and Drug Administration (FDA)-labeled dosing. There were no significant differences in incidence of stroke (2.7% vs 2.2%), major bleeding (0% vs 0.7%), and CRNMB (2.7% vs 1.4%) in the off-label reduced dosing versus standard dosing groups. All-cause mortality was higher in the off-label reduced-dose group (16 [10.9%] vs 2 [1.4%], P < 0.05). Older adults with nonvalvular AF are commonly prescribed lower-than-recommended doses of apixaban. However, no significant association was found between empiric off-label reduced dosing and stroke or bleeding outcomes.

The whole and its parts: Visualizing Gaussian mixture models

Gaussian mixture models are classical but still popular machine learning models. An appealing feature of Gaussian mixture models is their tractability, that is, they can be learned efficiently and exactly from data, and also support efficient exact inference queries like soft clustering data points. Only seemingly simple, Gaussian mixture models can be hard to understand. There are at least four aspects to understanding Gaussian mixture models, namely, understanding the whole distribution, its individual parts (mixture components), the relationships between the parts, and the interplay of the whole and its parts. In a structured literature review of applications of Gaussian mixture models, we found the need for supporting all four aspects. To identify candidate visualizations that effectively aid the user needs, we structure the available design space along three different representations of Gaussian mixture models, namely as functions, sets of parameters, and sampling processes. From the design space, we implemented three design concepts that visualize the overall distribution together with its components. Finally, we assessed the practical usefulness of the design concepts with respect to the different user needs in expert interviews and an insight-based user study.

Exact Bayesian Inference for Loopy Probabilistic Programs using Generating Functions

We present an exact Bayesian inference method for inferring posterior distributions encoded by probabilistic programs featuring possibly unbounded loops . Our method is built on a denotational semantics represented by probability generating functions , which resolves semantic intricacies induced by intertwining discrete probabilistic loops with conditioning (for encoding posterior observations). We implement our method in a tool called Prodigy; it augments existing computer algebra systems with the theory of generating functions for the (semi-)automatic inference and quantitative verification of conditioned probabilistic programs. Experimental results show that Prodigy can handle various infinite-state loopy programs and exhibits comparable performance to state-of-the-art exact inference tools over loop-free benchmarks.

Exact post-selection inference for adjusted R squared selection

Post-selection inference is developed for regression coefficients selected by the widely used model selection technique of adjusted R2. Selective inference deals with the selection aspect by conditioning inference on the model selection event. In linear models, we obtain exact post-selection inference in finite samples. Extensions to logistic regression models are discussed. A simulation study illustrates the exact type I error control, unlike classical inference. Our tests provide higher power than data splitting approaches.

Sensitivity analysis for matched observational studies with continuous exposures and binary outcomes

Summary Matching is one of the most widely used study designs for adjusting for measured confounders in observational studies. However, unmeasured confounding may exist and cannot be removed by matching. Therefore, a sensitivity analysis is typically needed to assess a causal conclusion’s sensitivity to unmeasured confounding. Sensitivity analysis frameworks for binary exposures have been well-established for various matching designs and are commonly used in various studies. However, unlike the binary exposure case, there still lacks valid and general sensitivity analysis methods for continuous exposures, except in some special cases such as pair matching. To fill this gap in the binary outcome case, we develop a sensitivity analysis framework for general matching designs with continuous exposures and binary outcomes. First, we use probabilistic lattice theory to show our sensitivity analysis approach is finite-population- exact under Fisher’s sharp null. Second, we prove a novel design sensitivity formula as a powerful tool for asymptotically evaluating the performance of our sensitivity analysis approach. Third, to allow effect heterogeneity with binary outcomes, we introduce a framework for conducting asymptotically exact inference and sensitivity analysis on generalized attributable effects with binary outcomes via mixed- integer programming. Fourth, for the continuous outcomes case, we show that conducting an asymptotically exact sensitivity analysis in matched observational studies when both the exposures and outcomes are continuous is generally NP-hard, except in some special cases such as pair matching. As a real data application, we apply our new methods to study the effect of early-life lead exposure on juvenile delinquency. An implementation of the methods in this work is available in the R package doseSens.

Exact selective inference with randomization

Summary We introduce a pivot for exact selective inference with randomization. Not only does our pivot lead to exact inference in Gaussian regression models, but it is also available in closed form. We reduce this problem to inference for a bivariate truncated Gaussian variable. By doing so, we give up some power that is achieved with approximate maximum likelihood estimation in Panigrahi &amp; Taylor (2023). Yet our pivot always produces narrower confidence intervals than a closely related data-splitting procedure. We investigate the trade-off between power and exact selective inference on simulated datasets and an HIV drug resistance dataset.